http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/explainuser_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out index 3675d8d..5f5f5f6 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out @@ -303,124 +303,126 @@ Stage-0 limit:100 Stage-1 Reducer 5 vectorized, llap - File Output Operator [FS_216] - Limit [LIM_215] (rows=12 width=285) + File Output Operator [FS_217] + Limit [LIM_216] (rows=12 width=285) Number of rows:100 - Select Operator [SEL_214] (rows=12 width=285) + Select Operator [SEL_215] (rows=12 width=285) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 4 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_213] - Group By Operator [GBY_212] (rows=12 width=285) + SHUFFLE [RS_214] + Group By Operator [GBY_213] (rows=12 width=285) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2 Group By Operator [GBY_48] (rows=12 width=285) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col11)","count(_col21)","count(_col3)"],keys:_col10, _col20, _col2 - Merge Join Operator [MERGEJOIN_187] (rows=9275 width=534) - Conds:RS_44._col1, _col3=RS_45._col15, _col17(Inner),Output:["_col2","_col3","_col10","_col11","_col20","_col21"] - <-Reducer 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_45] - PartitionCols:_col15, _col17 - Select Operator [SEL_40] (rows=420 width=447) - Output:["_col4","_col5","_col14","_col15","_col17"] - Merge Join Operator [MERGEJOIN_186] (rows=420 width=447) - Conds:RS_37._col4, _col2=RS_38._col4, _col2(Inner),Output:["_col0","_col1","_col14","_col15","_col17"] - <-Reducer 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_38] - PartitionCols:_col4, _col2 - Merge Join Operator [MERGEJOIN_185] (rows=10 width=356) - Conds:RS_211._col0=RS_199._col0(Inner),Output:["_col2","_col3","_col4","_col5"] - <-Map 6 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_199] - PartitionCols:_col0 - Select Operator [SEL_196] (rows=25 width=178) - Output:["_col0"] - Filter Operator [FIL_193] (rows=25 width=178) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - TableScan [TS_3] (rows=500 width=178) - default@src,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Map 15 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_211] - PartitionCols:_col0 - Select Operator [SEL_210] (rows=7 width=531) - Output:["_col0","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_209] (rows=7 width=534) - predicate:((v1 = 'srv1') and k1 is not null and k2 is not null and k3 is not null and v2 is not null and v3 is not null) - TableScan [TS_18] (rows=85 width=534) - default@sr,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] - <-Reducer 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_37] - PartitionCols:_col4, _col2 - Merge Join Operator [MERGEJOIN_184] (rows=42 width=352) - Conds:RS_34._col1=RS_208._col1(Inner),Output:["_col0","_col1","_col2","_col4"] - <-Map 14 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_208] - PartitionCols:_col1 - Select Operator [SEL_207] (rows=2 width=180) - Output:["_col1"] - Filter Operator [FIL_206] (rows=2 width=175) - predicate:((key = 'src1key') and value is not null) - TableScan [TS_15] (rows=25 width=175) - default@src1,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 8 [SIMPLE_EDGE] llap - SHUFFLE [RS_34] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_183] (rows=42 width=352) - Conds:RS_31._col3=RS_205._col1(Inner),Output:["_col0","_col1","_col2","_col4"] - <-Map 13 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_205] - PartitionCols:_col1 - Select Operator [SEL_204] (rows=6 width=185) - Output:["_col1"] - Filter Operator [FIL_203] (rows=6 width=178) - predicate:((key = 'srcpartkey') and value is not null) - TableScan [TS_12] (rows=2000 width=178) - default@srcpart,srcpart,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 7 [SIMPLE_EDGE] llap - SHUFFLE [RS_31] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_182] (rows=7 width=443) - Conds:RS_202._col0=RS_198._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Map 6 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_198] - PartitionCols:_col0 - Select Operator [SEL_195] (rows=2 width=178) - Output:["_col0"] - Filter Operator [FIL_192] (rows=2 width=178) - predicate:((value = 'd1value') and key is not null) - Please refer to the previous TableScan [TS_3] - <-Map 12 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_202] - PartitionCols:_col0 - Select Operator [SEL_201] (rows=7 width=531) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_200] (rows=7 width=534) - predicate:((v3 = 'ssv3') and k1 is not null and k2 is not null and k3 is not null and v1 is not null and v2 is not null) - TableScan [TS_6] (rows=85 width=534) - default@ss_n1,ss_n1,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] - <-Reducer 2 [SIMPLE_EDGE] llap - SHUFFLE [RS_44] - PartitionCols:_col1, _col3 - Merge Join Operator [MERGEJOIN_181] (rows=265 width=269) - Conds:RS_190._col0=RS_197._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 6 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_197] - PartitionCols:_col0 - Select Operator [SEL_194] (rows=25 width=178) - Output:["_col0"] - Filter Operator [FIL_191] (rows=25 width=178) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - Please refer to the previous TableScan [TS_3] - <-Map 1 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_190] - PartitionCols:_col0 - Select Operator [SEL_189] (rows=170 width=356) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_188] (rows=170 width=356) - predicate:(k1 is not null and v2 is not null and v3 is not null) - TableScan [TS_0] (rows=170 width=356) - default@cs,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v2","k3","v3"] + Top N Key Operator [TNK_91] (rows=9275 width=534) + keys:_col10, _col20, _col2,sort order:+++,top n:100 + Merge Join Operator [MERGEJOIN_188] (rows=9275 width=534) + Conds:RS_44._col1, _col3=RS_45._col15, _col17(Inner),Output:["_col2","_col3","_col10","_col11","_col20","_col21"] + <-Reducer 10 [SIMPLE_EDGE] llap + SHUFFLE [RS_45] + PartitionCols:_col15, _col17 + Select Operator [SEL_40] (rows=420 width=447) + Output:["_col4","_col5","_col14","_col15","_col17"] + Merge Join Operator [MERGEJOIN_187] (rows=420 width=447) + Conds:RS_37._col4, _col2=RS_38._col4, _col2(Inner),Output:["_col0","_col1","_col14","_col15","_col17"] + <-Reducer 11 [SIMPLE_EDGE] llap + SHUFFLE [RS_38] + PartitionCols:_col4, _col2 + Merge Join Operator [MERGEJOIN_186] (rows=10 width=356) + Conds:RS_212._col0=RS_200._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + <-Map 6 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_200] + PartitionCols:_col0 + Select Operator [SEL_197] (rows=25 width=178) + Output:["_col0"] + Filter Operator [FIL_194] (rows=25 width=178) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + TableScan [TS_3] (rows=500 width=178) + default@src,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Map 15 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_212] + PartitionCols:_col0 + Select Operator [SEL_211] (rows=7 width=531) + Output:["_col0","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_210] (rows=7 width=534) + predicate:((v1 = 'srv1') and k1 is not null and k2 is not null and k3 is not null and v2 is not null and v3 is not null) + TableScan [TS_18] (rows=85 width=534) + default@sr,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] + <-Reducer 9 [SIMPLE_EDGE] llap + SHUFFLE [RS_37] + PartitionCols:_col4, _col2 + Merge Join Operator [MERGEJOIN_185] (rows=42 width=352) + Conds:RS_34._col1=RS_209._col1(Inner),Output:["_col0","_col1","_col2","_col4"] + <-Map 14 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_209] + PartitionCols:_col1 + Select Operator [SEL_208] (rows=2 width=180) + Output:["_col1"] + Filter Operator [FIL_207] (rows=2 width=175) + predicate:((key = 'src1key') and value is not null) + TableScan [TS_15] (rows=25 width=175) + default@src1,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_34] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_184] (rows=42 width=352) + Conds:RS_31._col3=RS_206._col1(Inner),Output:["_col0","_col1","_col2","_col4"] + <-Map 13 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_206] + PartitionCols:_col1 + Select Operator [SEL_205] (rows=6 width=185) + Output:["_col1"] + Filter Operator [FIL_204] (rows=6 width=178) + predicate:((key = 'srcpartkey') and value is not null) + TableScan [TS_12] (rows=2000 width=178) + default@srcpart,srcpart,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 7 [SIMPLE_EDGE] llap + SHUFFLE [RS_31] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_183] (rows=7 width=443) + Conds:RS_203._col0=RS_199._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] + <-Map 6 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_199] + PartitionCols:_col0 + Select Operator [SEL_196] (rows=2 width=178) + Output:["_col0"] + Filter Operator [FIL_193] (rows=2 width=178) + predicate:((value = 'd1value') and key is not null) + Please refer to the previous TableScan [TS_3] + <-Map 12 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_203] + PartitionCols:_col0 + Select Operator [SEL_202] (rows=7 width=531) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_201] (rows=7 width=534) + predicate:((v3 = 'ssv3') and k1 is not null and k2 is not null and k3 is not null and v1 is not null and v2 is not null) + TableScan [TS_6] (rows=85 width=534) + default@ss_n1,ss_n1,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_44] + PartitionCols:_col1, _col3 + Merge Join Operator [MERGEJOIN_182] (rows=265 width=269) + Conds:RS_191._col0=RS_198._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 6 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_198] + PartitionCols:_col0 + Select Operator [SEL_195] (rows=25 width=178) + Output:["_col0"] + Filter Operator [FIL_192] (rows=25 width=178) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + Please refer to the previous TableScan [TS_3] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_191] + PartitionCols:_col0 + Select Operator [SEL_190] (rows=170 width=356) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_189] (rows=170 width=356) + predicate:(k1 is not null and v2 is not null and v3 is not null) + TableScan [TS_0] (rows=170 width=356) + default@cs,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v2","k3","v3"] PREHOOK: query: explain SELECT x.key, z.value, y.value @@ -992,105 +994,107 @@ Stage-0 limit:100 Stage-1 Reducer 7 vectorized, llap - File Output Operator [FS_232] - Limit [LIM_231] (rows=100 width=10) + File Output Operator [FS_234] + Limit [LIM_233] (rows=100 width=10) Number of rows:100 - Select Operator [SEL_230] (rows=732 width=10) + Select Operator [SEL_232] (rows=732 width=10) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 6 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_229] - Group By Operator [GBY_228] (rows=732 width=10) + SHUFFLE [RS_231] + Group By Operator [GBY_230] (rows=732 width=10) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Map 5 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_227] + SHUFFLE [RS_229] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_226] (rows=1464 width=10) + Group By Operator [GBY_228] (rows=1464 width=10) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col11)","count(_col21)","count(_col3)"],keys:_col10, _col20, _col2 - Map Join Operator [MAPJOIN_225] (rows=1464 width=10) - Conds:RS_208._col1, _col3=SEL_224._col15, _col17(Inner),Output:["_col2","_col3","_col10","_col11","_col20","_col21"] - <-Map 2 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_208] - PartitionCols:_col1, _col3 - Map Join Operator [MAPJOIN_207] (rows=275 width=10) - Conds:RS_204._col0=SEL_206._col0(Inner),Output:["_col1","_col2","_col3"] - <-Map 1 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_204] - PartitionCols:_col0 - Select Operator [SEL_203] (rows=170 width=34) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_202] (rows=170 width=34) - predicate:(k1 is not null and v2 is not null and v3 is not null) - TableScan [TS_0] (rows=170 width=34) - default@cs,cs,Tbl:COMPLETE,Col:NONE,Output:["k1","v2","k3","v3"] - <-Select Operator [SEL_206] (rows=250 width=10) - Output:["_col0"] - Filter Operator [FIL_205] (rows=250 width=10) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - TableScan [TS_3] (rows=500 width=10) - default@src,d3,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_224] (rows=1331 width=10) - Output:["_col4","_col5","_col14","_col15","_col17"] - Map Join Operator [MAPJOIN_223] (rows=1331 width=10) - Conds:MAPJOIN_222._col4, _col2=RS_218._col4, _col2(Inner),Output:["_col0","_col1","_col14","_col15","_col17"] - <-Map 10 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_218] - PartitionCols:_col4, _col2 - Map Join Operator [MAPJOIN_217] (rows=275 width=10) - Conds:RS_214._col0=SEL_216._col0(Inner),Output:["_col2","_col3","_col4","_col5"] - <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_214] - PartitionCols:_col0 - Select Operator [SEL_213] (rows=42 width=34) - Output:["_col0","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_212] (rows=42 width=34) - predicate:((v1 = 'srv1') and k1 is not null and k2 is not null and k3 is not null and v2 is not null and v3 is not null) - TableScan [TS_18] (rows=85 width=34) - default@sr,sr,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] - <-Select Operator [SEL_216] (rows=250 width=10) - Output:["_col0"] - Filter Operator [FIL_215] (rows=250 width=10) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - TableScan [TS_21] (rows=500 width=10) - default@src,d2,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_222] (rows=1210 width=10) - Conds:MAPJOIN_221._col1=RS_211._col1(Inner),Output:["_col0","_col1","_col2","_col4"] - <-Map 8 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_211] - PartitionCols:_col1 - Select Operator [SEL_210] (rows=12 width=7) - Output:["_col1"] - Filter Operator [FIL_209] (rows=12 width=7) - predicate:((key = 'src1key') and value is not null) - TableScan [TS_15] (rows=25 width=7) - default@src1,src1,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_221] (rows=1100 width=10) - Conds:RS_201._col3=SEL_220._col1(Inner),Output:["_col0","_col1","_col2","_col4"] - <-Map 4 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_201] - PartitionCols:_col3 - Map Join Operator [MAPJOIN_200] (rows=275 width=10) - Conds:RS_197._col0=SEL_199._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] - <-Map 3 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_197] - PartitionCols:_col0 - Select Operator [SEL_196] (rows=42 width=34) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_195] (rows=42 width=34) - predicate:((v3 = 'ssv3') and k1 is not null and k2 is not null and k3 is not null and v1 is not null and v2 is not null) - TableScan [TS_6] (rows=85 width=34) - default@ss_n1,ss_n1,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] - <-Select Operator [SEL_199] (rows=250 width=10) - Output:["_col0"] - Filter Operator [FIL_198] (rows=250 width=10) - predicate:((value = 'd1value') and key is not null) - TableScan [TS_9] (rows=500 width=10) - default@src,d1,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_220] (rows=1000 width=10) - Output:["_col1"] - Filter Operator [FIL_219] (rows=1000 width=10) - predicate:((key = 'srcpartkey') and value is not null) - TableScan [TS_12] (rows=2000 width=10) - default@srcpart,srcpart,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + Top N Key Operator [TNK_227] (rows=1464 width=10) + keys:_col10, _col20, _col2,sort order:+++,top n:100 + Map Join Operator [MAPJOIN_226] (rows=1464 width=10) + Conds:RS_209._col1, _col3=SEL_225._col15, _col17(Inner),Output:["_col2","_col3","_col10","_col11","_col20","_col21"] + <-Map 2 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_209] + PartitionCols:_col1, _col3 + Map Join Operator [MAPJOIN_208] (rows=275 width=10) + Conds:RS_205._col0=SEL_207._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_205] + PartitionCols:_col0 + Select Operator [SEL_204] (rows=170 width=34) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_203] (rows=170 width=34) + predicate:(k1 is not null and v2 is not null and v3 is not null) + TableScan [TS_0] (rows=170 width=34) + default@cs,cs,Tbl:COMPLETE,Col:NONE,Output:["k1","v2","k3","v3"] + <-Select Operator [SEL_207] (rows=250 width=10) + Output:["_col0"] + Filter Operator [FIL_206] (rows=250 width=10) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + TableScan [TS_3] (rows=500 width=10) + default@src,d3,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_225] (rows=1331 width=10) + Output:["_col4","_col5","_col14","_col15","_col17"] + Map Join Operator [MAPJOIN_224] (rows=1331 width=10) + Conds:MAPJOIN_223._col4, _col2=RS_219._col4, _col2(Inner),Output:["_col0","_col1","_col14","_col15","_col17"] + <-Map 10 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_219] + PartitionCols:_col4, _col2 + Map Join Operator [MAPJOIN_218] (rows=275 width=10) + Conds:RS_215._col0=SEL_217._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + <-Map 9 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_215] + PartitionCols:_col0 + Select Operator [SEL_214] (rows=42 width=34) + Output:["_col0","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_213] (rows=42 width=34) + predicate:((v1 = 'srv1') and k1 is not null and k2 is not null and k3 is not null and v2 is not null and v3 is not null) + TableScan [TS_18] (rows=85 width=34) + default@sr,sr,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] + <-Select Operator [SEL_217] (rows=250 width=10) + Output:["_col0"] + Filter Operator [FIL_216] (rows=250 width=10) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + TableScan [TS_21] (rows=500 width=10) + default@src,d2,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Map Join Operator [MAPJOIN_223] (rows=1210 width=10) + Conds:MAPJOIN_222._col1=RS_212._col1(Inner),Output:["_col0","_col1","_col2","_col4"] + <-Map 8 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_212] + PartitionCols:_col1 + Select Operator [SEL_211] (rows=12 width=7) + Output:["_col1"] + Filter Operator [FIL_210] (rows=12 width=7) + predicate:((key = 'src1key') and value is not null) + TableScan [TS_15] (rows=25 width=7) + default@src1,src1,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Map Join Operator [MAPJOIN_222] (rows=1100 width=10) + Conds:RS_202._col3=SEL_221._col1(Inner),Output:["_col0","_col1","_col2","_col4"] + <-Map 4 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_202] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_201] (rows=275 width=10) + Conds:RS_198._col0=SEL_200._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4"] + <-Map 3 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_198] + PartitionCols:_col0 + Select Operator [SEL_197] (rows=42 width=34) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_196] (rows=42 width=34) + predicate:((v3 = 'ssv3') and k1 is not null and k2 is not null and k3 is not null and v1 is not null and v2 is not null) + TableScan [TS_6] (rows=85 width=34) + default@ss_n1,ss_n1,Tbl:COMPLETE,Col:NONE,Output:["k1","v1","k2","v2","k3","v3"] + <-Select Operator [SEL_200] (rows=250 width=10) + Output:["_col0"] + Filter Operator [FIL_199] (rows=250 width=10) + predicate:((value = 'd1value') and key is not null) + TableScan [TS_9] (rows=500 width=10) + default@src,d1,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_221] (rows=1000 width=10) + Output:["_col1"] + Filter Operator [FIL_220] (rows=1000 width=10) + predicate:((key = 'srcpartkey') and value is not null) + TableScan [TS_12] (rows=2000 width=10) + default@srcpart,srcpart,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: explain SELECT x.key, z.value, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out index 1463b32..252831e 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out @@ -199,19 +199,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -295,19 +300,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1), count(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + aggregations: sum(_col1), count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double), _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -395,17 +405,22 @@ STAGE PLANS: expressions: cdouble (type: double) outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator + Top N Key Operator + sort order: + keys: cdouble (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + keys: cdouble (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -415,13 +430,13 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -921,26 +936,42 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() + Top N Key Operator + sort order: + keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + top n: 2 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: bigint) - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: bigint) + Top N Key Operator + sort order: + + keys: key (type: string) + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + top n: 3 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out index 260ce3d..1027bfe 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out @@ -200,19 +200,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -310,19 +315,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1), count(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + aggregations: sum(_col1), count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double), _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -424,17 +434,22 @@ STAGE PLANS: expressions: cdouble (type: double) outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator + Top N Key Operator + sort order: + keys: cdouble (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + keys: cdouble (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 Execution mode: vectorized, llap LLAP IO: all inputs Reducer 2 @@ -444,11 +459,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 Execution mode: vectorized, llap @@ -456,13 +471,13 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/llap_decimal64_reader.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/llap_decimal64_reader.q.out b/ql/src/test/results/clientpositive/llap/llap_decimal64_reader.q.out index 0041206..88ddd9c 100644 --- a/ql/src/test/results/clientpositive/llap/llap_decimal64_reader.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_decimal64_reader.q.out @@ -131,17 +131,22 @@ STAGE PLANS: Filter Operator predicate: ((cdecimal1 = 3.35) or (cdecimal1 = 4.46)) (type: boolean) Statistics: Num rows: 24576 Data size: 5505024 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator + Top N Key Operator + sort order: ++ keys: cdecimal1 (type: decimal(10,2)), cdecimal2 (type: decimal(38,5)) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + Statistics: Num rows: 24576 Data size: 5505024 Basic stats: COMPLETE Column stats: COMPLETE + top n: 2 + Group By Operator + keys: cdecimal1 (type: decimal(10,2)), cdecimal2 (type: decimal(38,5)) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + Reduce Output Operator + key expressions: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -227,17 +232,22 @@ STAGE PLANS: Filter Operator predicate: ((cdecimal1 = 3.35) or (cdecimal1 = 4.46)) (type: boolean) Statistics: Num rows: 24576 Data size: 5505024 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator + Top N Key Operator + sort order: ++ keys: cdecimal1 (type: decimal(10,2)), cdecimal2 (type: decimal(38,5)) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) - sort order: ++ - Map-reduce partition columns: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + Statistics: Num rows: 24576 Data size: 5505024 Basic stats: COMPLETE Column stats: COMPLETE + top n: 2 + Group By Operator + keys: cdecimal1 (type: decimal(10,2)), cdecimal2 (type: decimal(38,5)) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 + Reduce Output Operator + key expressions: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + sort order: ++ + Map-reduce partition columns: _col0 (type: decimal(10,2)), _col1 (type: decimal(38,5)) + Statistics: Num rows: 2 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/offset_limit.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/offset_limit.q.out b/ql/src/test/results/clientpositive/llap/offset_limit.q.out index 0e718fd..97d2ac2 100644 --- a/ql/src/test/results/clientpositive/llap/offset_limit.q.out +++ b/ql/src/test/results/clientpositive/llap/offset_limit.q.out @@ -26,19 +26,24 @@ STAGE PLANS: expressions: key (type: string), substr(value, 5) (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 20 + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: double) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs Reducer 2 http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out index 4c62d7f..2e8d5f3 100644 --- a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out +++ b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out @@ -201,19 +201,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 30 + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -298,19 +303,24 @@ STAGE PLANS: expressions: value (type: string), (UDFToDouble(key) + 1.0D) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(_col1), count(_col1) + Top N Key Operator + sort order: + keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + top n: 30 + Group By Operator + aggregations: sum(_col1), count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: double), _col2 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 250 Data size: 26750 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 + value expressions: _col1 (type: double), _col2 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -399,17 +409,22 @@ STAGE PLANS: expressions: cdouble (type: double) outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator + Top N Key Operator + sort order: + keys: cdouble (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + - Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE - TopN Hash Memory Usage: 0.3 + Statistics: Num rows: 12288 Data size: 73400 Basic stats: COMPLETE Column stats: COMPLETE + top n: 30 + Group By Operator + keys: cdouble (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE + TopN Hash Memory Usage: 0.3 Execution mode: llap LLAP IO: all inputs Reducer 2 @@ -419,14 +434,14 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 21816 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 20 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/orc_struct_type_vectorization.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_struct_type_vectorization.q.out b/ql/src/test/results/clientpositive/llap/orc_struct_type_vectorization.q.out index 5c6b481..a804e3c 100644 --- a/ql/src/test/results/clientpositive/llap/orc_struct_type_vectorization.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_struct_type_vectorization.q.out @@ -238,31 +238,40 @@ STAGE PLANS: projectedOutputColumnNums: [4] selectExpressions: VectorUDFStructField(col 1:struct<f1:int,f2:string>, col 0:int) -> 4:int Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 4:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 4:int - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] + Top N Key Operator + sort order: + keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + top n: 10 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 4:int + native: true + Group By Operator + aggregations: sum(_col0) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 4:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 4:int + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 341 Data size: 76542 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/851c8aba/ql/src/test/results/clientpositive/llap/parquet_complex_types_vectorization.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/parquet_complex_types_vectorization.q.out b/ql/src/test/results/clientpositive/llap/parquet_complex_types_vectorization.q.out index da9dd4e..baeb60e 100644 --- a/ql/src/test/results/clientpositive/llap/parquet_complex_types_vectorization.q.out +++ b/ql/src/test/results/clientpositive/llap/parquet_complex_types_vectorization.q.out @@ -214,31 +214,40 @@ STAGE PLANS: projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 7:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:int - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] + Top N Key Operator + sort order: + keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + top n: 10 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 6:int + native: true + Group By Operator + aggregations: sum(_col1) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 7:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:int + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 341 Data size: 38920 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs (cache only) Map Vectorization: @@ -503,31 +512,40 @@ STAGE PLANS: projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 7:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:int - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] + Top N Key Operator + sort order: + keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + top n: 10 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 6:int + native: true + Group By Operator + aggregations: sum(_col1) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 7:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:int + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 341 Data size: 38921 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs (cache only) Map Vectorization: @@ -792,31 +810,40 @@ STAGE PLANS: projectedOutputColumnNums: [6, 7] selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col1) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 7:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 6:int - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] + Top N Key Operator + sort order: + keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + top n: 10 + Top N Key Vectorization: + className: VectorTopNKeyOperator + keyExpressions: col 6:int + native: true + Group By Operator + aggregations: sum(_col1) + Group By Vectorization: + aggregators: VectorUDAFSumLong(col 7:int) -> bigint + className: VectorGroupByOperator + groupByMode: HASH + keyExpressions: col 6:int + native: false + vectorProcessingMode: HASH + projectedOutputColumnNums: [0] + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + native: true + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + Statistics: Num rows: 341 Data size: 38923 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs (cache only) Map Vectorization:
